CN113627546A - Method for determining reflectivity data, method for determining electric quantity and related device - Google Patents
Method for determining reflectivity data, method for determining electric quantity and related device Download PDFInfo
- Publication number
- CN113627546A CN113627546A CN202110938005.9A CN202110938005A CN113627546A CN 113627546 A CN113627546 A CN 113627546A CN 202110938005 A CN202110938005 A CN 202110938005A CN 113627546 A CN113627546 A CN 113627546A
- Authority
- CN
- China
- Prior art keywords
- data
- period
- snow
- weather
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000002310 reflectometry Methods 0.000 title claims abstract description 171
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000012545 processing Methods 0.000 claims abstract description 65
- 238000009825 accumulation Methods 0.000 claims description 124
- 238000012549 training Methods 0.000 claims description 45
- 238000012216 screening Methods 0.000 claims description 19
- 238000010248 power generation Methods 0.000 claims description 18
- 230000006641 stabilisation Effects 0.000 claims description 15
- 238000011105 stabilization Methods 0.000 claims description 15
- 230000001932 seasonal effect Effects 0.000 claims description 9
- 230000000087 stabilizing effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 83
- 238000001556 precipitation Methods 0.000 description 22
- 206010027336 Menstruation delayed Diseases 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a determination method of reflectivity data, an electric quantity determination method and a related device, which can predict the ground reflectivity data of a data missing time period by using a data processing model when the ground reflectivity data of a certain time period is missing, and further can determine the generated energy of a double-sided photovoltaic module by using the ground reflectivity data. Further, in the method and the device, before the ground reflectivity data is predicted, the weather state time period corresponding to the data missing time period is determined based on the weather data corresponding to the data missing time period, and then the data processing model matched with the weather state time period is selected, so that the called data processing model considers the weather state of the data missing time period, and the accuracy of the data processing model is improved.
Description
Technical Field
The invention relates to the field of determination of ground reflectivity data, in particular to a determination method of reflectivity data, an electric quantity determination method and a related device.
Background
Currently, the ground reflectivity data can be determined by means of satellite inversion. The satellite inversion refers to that the satellite reversely deduces ground reflectivity data through shot ground image data, outputs the ground reflectivity data to the power generation capacity determining device, and the power generation capacity determining device can determine the power generation capacity of the double-sided photovoltaic module according to the output ground reflectivity data.
In practical application, the ground reflectivity data of a certain time period is lost due to shielding of an air shelter, satellite data acquisition delay and the like, and the generated energy determining device cannot determine the generated energy of the double-sided photovoltaic module corresponding to the ground reflectivity data of the time period.
Disclosure of Invention
In view of this, the present invention provides a method for determining reflectivity data, a method for determining power consumption, and a related device, so as to solve the problem that if the ground reflectivity data of a certain time period is missing, the power generation amount of the double-sided photovoltaic module corresponding to the ground reflectivity data of the time period cannot be determined.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method of determining reflectivity data, comprising:
acquiring a data missing time period and acquiring weather data corresponding to the data missing time period;
determining a weather state period corresponding to the data missing time period based on the weather data;
acquiring a data processing model corresponding to the weather state time period, and calling the data processing model to process the weather data to obtain the ground reflectivity data of the data missing time period;
the data processing model is obtained based on training of a training sample; the training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
Optionally, determining, based on the weather data, a weather state period corresponding to the data missing time period includes:
acquiring preset weather state time periods and a determination rule of the weather state time periods; each weather state time interval comprises a non-snow accumulation period, a snow accumulation early period, a snow accumulation stabilization period and a snow accumulation later period; the non-snow period comprises at least one non-snow time period;
and judging the weather data corresponding to the data missing time period according to the determination rule of the weather state time period so as to determine the weather state time period corresponding to the data missing time period.
Optionally, in the case that the non-snowy period includes a plurality of non-snowy periods, the non-snowy periods include a pre-non-snowy period, a mid-non-snowy period, or a post-non-snowy period.
Optionally, the data processing models corresponding to different weather condition periods are different, and the generation process of the data processing model includes:
obtaining a training sample; the training samples comprise weather data samples corresponding to the weather state period and ground reflectivity data samples;
and training a data processing model by using the training samples until a preset training stopping condition is reached.
Optionally, obtaining training samples comprises:
acquiring an initial weather data sample corresponding to the weather state time period; the initial weather data sample comprises weather data of a plurality of indexes at different time periods;
screening out key indexes corresponding to the weather state time periods from the multiple indexes on the basis of the weather data of the multiple indexes at different time periods;
taking the weather data of the key indexes at different time periods as weather data samples corresponding to the weather state time periods;
and acquiring a ground reflectivity data sample corresponding to each time period in the weather data samples.
Optionally, obtaining an initial weather data sample corresponding to the weather state period includes:
dividing the historical year into a non-snow accumulation early stage, a non-snow accumulation middle stage, a non-snow accumulation later stage, a snow accumulation early stage, a snow accumulation stabilization stage and a snow accumulation later stage based on the preset weather state periods and the determination rule of the weather state periods;
acquiring initial weather data samples respectively corresponding to the early stage of non-accumulated snow, the middle stage of non-accumulated snow, the late stage of non-accumulated snow, the early stage of accumulated snow, the stable stage of accumulated snow and the late stage of accumulated snow in the historical year;
and screening out the initial weather data samples corresponding to the weather state time period from the initial weather data samples.
Optionally, based on the preset weather state periods and the determination rule of the weather state periods, splitting the historical year into a non-snow early stage, a non-snow middle stage, a non-snow late stage, a snow early stage, a snow stabilization stage and a snow late stage, including:
dividing the historical years into a non-snow period, a snow accumulation early period, a snow accumulation stabilizing period and a snow accumulation later period based on the preset weather state periods and the determination rule of the weather state periods;
according to the seasonal information of the historical year, dividing the non-snowy period into an initial non-snowy early period, an initial non-snowy middle period and an initial non-snowy later period;
correcting a first demarcation time point of the initial early stage of non-snow and the initial middle stage of non-snow, and a second demarcation time point of the initial middle stage of non-snow and the initial late stage of non-snow;
and splitting the non-snow accumulation period by using the corrected first boundary time point and the second boundary time point to obtain a non-snow accumulation early stage, a non-snow accumulation middle stage and a non-snow accumulation later stage.
Optionally, screening out a key index corresponding to the weather state period from the multiple indexes based on the weather data of the multiple indexes at different time periods, including:
performing correlation calculation on the weather data of the multiple indexes at different time periods to obtain correlation among the multiple indexes;
and screening out indexes meeting preset correlation rule from the indexes based on the correlation among the indexes, and using the indexes as key indexes corresponding to the weather state time period.
A power determination method, comprising:
acquiring the ground reflectivity data of the data missing time period; the ground reflectivity data is determined by the method for determining the reflectivity data;
and determining the power generation capacity of the double-sided photovoltaic module by using the ground reflectivity data.
A reflectivity data determining apparatus, comprising:
the weather data acquisition module is used for acquiring a data missing time period and acquiring weather data corresponding to the data missing time period;
the time interval determining module is used for determining a weather state time interval corresponding to the data missing time interval based on the weather data;
the data determining module is used for acquiring a data processing model corresponding to the weather state time period and calling the data processing model to process the weather data to obtain the ground reflectivity data of the data missing time period;
the data processing model is obtained based on training of a training sample; the training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
An electrical quantity determination device comprising:
the reflectivity data acquisition module is used for acquiring the ground reflectivity data of the data missing time period; the ground reflectivity data is determined by the method for determining the reflectivity data;
and the power generation capacity determining module is used for determining the power generation capacity of the double-sided photovoltaic module by using the ground reflectivity data.
A storage medium comprising a stored program, wherein the program, when executed, controls a device in which the storage medium is located to execute the above-mentioned method for determining reflectivity data or to execute the above-mentioned method for determining power.
An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used for executing the determination method of the reflectivity data or executing the electric quantity determination method.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a determination method of reflectivity data, an electric quantity determination method and a related device, which can predict the ground reflectivity data of a data missing time period by using a data processing model when the ground reflectivity data of a certain time period is missing, and further can determine the generated energy of a double-sided photovoltaic module by using the ground reflectivity data. Further, in the method and the device, before the ground reflectivity data is predicted, the weather state time period corresponding to the data missing time period is determined based on the weather data corresponding to the data missing time period, and then the data processing model matched with the weather state time period is selected, so that the called data processing model considers the weather state of the data missing time period, and the accuracy of the data processing model is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for determining reflectivity data according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for determining reflectivity data according to another embodiment of the present invention;
FIG. 3 is a schematic diagram of data of the reflectivity of a 201911-202002 ground surface in Haerbin Shuangcheng according to an embodiment of the present invention;
FIG. 4 is a data diagram of Gelin Qian' an 201912-202003 ground reflectivity according to an embodiment of the present invention;
fig. 5 is a schematic view of a scenario of a demarcation time point for non-snow season splitting according to an embodiment of the present invention;
FIG. 6 is a flowchart of a method for determining reflectivity data according to another embodiment of the present invention;
FIG. 7 is a flowchart of a method for determining reflectivity data according to another embodiment of the present invention;
fig. 8 is a flowchart of a method of determining reflectivity data according to a fifth embodiment of the present invention;
fig. 9 is a flowchart of a method of determining an electric quantity according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of an apparatus for determining reflectivity data according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an electric quantity determining apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In practical application, the ground reflectivity data of a certain time period is lost due to shielding of an air shelter, satellite data acquisition delay and the like, and the generated energy determining device cannot determine the generated energy of the double-sided photovoltaic module corresponding to the ground reflectivity data of the time period.
In order to solve the technical problem, the invention finds that interpolation can be used for complementing the ground reflectivity data, but in practical application, if interpolation is simply used for complementing the ground reflectivity data in different time periods, such as a snowing period and a non-snowing period, the accuracy of the complemented data is low.
In addition, in order to improve the accuracy of the supplemented data, a model, such as a neural network model, can be used for predicting the missing data, and the model can learn the characteristics of the data, so that the missing data can be accurately predicted. Furthermore, because the data of the ground reflectivity in different time periods are different, such as different snowfall and different duration of the snowfall in the front section, the middle section and the rear section of the snow accumulation period, the influence of factors such as temperature, humidity, precipitation, ground temperature and the like is caused, and the reflectivity is different, different models can be designed for different time periods, and the ground reflectivity data can be determined by adopting the corresponding models in the corresponding time periods, so that the accuracy of the determined ground reflectivity data can be further improved.
Specifically, in the embodiment of the invention, when the ground reflectivity data of a certain time period is missing, the data processing model can be used for predicting the ground reflectivity data of the data missing time period, and then the ground reflectivity data can be used for determining the power generation amount of the double-sided photovoltaic module. Further, in the method and the device, before the ground reflectivity data is predicted, the weather state time period corresponding to the data missing time period is determined based on the weather data corresponding to the data missing time period, and then the data processing model matched with the weather state time period is selected, so that the called data processing model considers the weather state of the data missing time period, and the accuracy of the data processing model is improved.
On the basis of the above, the embodiment of the present invention provides a method for determining reflectivity data, which can be applied to a controller, a processor, and other devices. Referring to fig. 1, the method of determining reflectivity data includes:
and S11, acquiring a data missing time period, and acquiring weather data corresponding to the data missing time period.
In this embodiment, the data missing time period may be calculated on a daily basis, and the ground reflectivity data may be missing for … … days on one or two days.
After the data missing time period is determined, weather data corresponding to the data missing time period is acquired, where the weather data in this embodiment may include:
the highest daily temperature, the lowest daily temperature, the ground temperature of 0cm, the amount of snow (the judgment standard is that precipitation occurs, and the amount of snow is the amount of precipitation when the day weather is snow instead of rain), precipitation data, humidity and the like.
It should be noted that the snowfall amount and the precipitation data may not be simultaneously present, for example, in winter, snowfall, only the snowfall amount and no precipitation data exist, and in summer, only the precipitation data and no precipitation data exist.
And S12, determining the weather state time period corresponding to the data missing time period based on the weather data.
In practical application, the existing weather condition periods comprise a non-snow accumulation period, a snow accumulation early period, a snow accumulation stabilization period and a snow accumulation late period; the non-snow period includes at least one non-snow time period.
In the case where the non-snowy period includes a plurality of non-snowy periods, the non-snowy period includes a pre-non-snowy period, a mid-non-snowy period, or a post-non-snowy period.
The weather state period corresponding to the data missing period in this embodiment may be one of the above-mentioned early stage of non-snow, middle stage of non-snow, late stage of non-snow, early stage of snow, stable stage of snow, and late stage of snow.
S13, acquiring a data processing model corresponding to the weather state time period, and calling the data processing model to process the weather data to obtain the ground reflectivity data of the data missing time period;
in this embodiment, the data processing models corresponding to different weather state periods are different.
The data processing model is obtained based on training of a training sample; the training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
The training samples of the data processing model comprise weather data samples corresponding to the weather state time periods and ground reflectivity data samples, so that when the weather data corresponding to the data missing time periods are input into the data processing model, the data processing model can output the ground reflectivity data of the data missing time periods.
When the data loss period is one day, the data processing model can obtain the ground reflectivity data of the day.
And when the data missing time period is multiple days, the data processing model sequentially obtains the ground reflectivity data of each of the multiple days.
In this embodiment, when the ground reflectivity data of a certain time period is missing, the data processing model can be used to predict the ground reflectivity data of the data missing time period, and thus the ground reflectivity data can be used to determine the power generation amount of the double-sided photovoltaic module. Further, in the method and the device, before the ground reflectivity data is predicted, the weather state time period corresponding to the data missing time period is determined based on the weather data corresponding to the data missing time period, and then the data processing model matched with the weather state time period is selected, so that the called data processing model considers the weather state of the data missing time period, and the accuracy of the data processing model is improved.
On the basis of the above, referring to fig. 2, the step S12 "determining the weather state period corresponding to the data missing time period based on the weather data" may include:
and S21, acquiring preset weather state time periods and a determination rule of the weather state time periods.
Each weather state time interval comprises a non-snow accumulation period, a snow accumulation early period, a snow accumulation stabilizing period and a snow accumulation later period; the non-snow period includes at least one non-snow time period. In the case where the non-snowy period includes a plurality of non-snowy periods, the non-snowy period includes a pre-non-snowy period, a mid-non-snowy period, or a post-non-snowy period.
In this embodiment, the early stage of non-snow, the middle stage of non-snow, the late stage of non-snow, the early stage of snow, the stable stage of snow and the late stage of snow make up the whole year.
In practical application, the whole year is generally divided into a non-snow accumulation period and a snow accumulation period, and in northern areas of China, the snow accumulation period is 11 months to 3-4 months in the next year. Two time division points are provided for the non-snow accumulation period and the snow accumulation period, one is the first day of the snow accumulation period, and the other is the last day of the snow accumulation period.
Searching backwards from a designated month (such as September), wherein the time of first occurrence of snowfall is the first day of the snow accumulation period, snowfall is performed for the last time, the ground reflectivity is continuously lower than the preset reflectivity value after snowfall, the first date lower than the preset reflectivity value is the last day of the snow accumulation period, if the ground reflectivity data is absent to influence judgment, the judgment condition is that the temperature is higher than the preset temperature value for a plurality of continuous days after snowfall, and the first date with the temperature higher than the preset temperature value is the last day of the snow accumulation.
The following different weather condition period determination processes are now introduced separately:
1) based on the preset weather state periods and the determination rules of the weather state periods, the historical years are divided into a non-snow period, a snow early period, a snow stable period and a snow late period.
1.1, early stage of accumulated snow.
And finding initial stable snowfall time from the first day of the snowfall period, if the condition that the ground reflectivity is continuously greater than the preset reflectivity value for multiple days after snowfall is met, determining the time that the ground reflectivity is continuously greater than the preset reflectivity value for multiple days after snowfall as the stable snowfall time, and then calling the first day from the first day of the snowfall period to the first day of the stable snowfall time as the early stage of snowfall. Otherwise, continuing to search backwards until finding a certain stable snowfall time.
If the data of the ground reflectivity before and after the initial stable snowfall are continuously lost and cannot be judged according to the ground reflectivity, whether the lowest air temperature of alpha days after the first day of snowfall and the ground temperature of 0cm are continuously lower than a preset temperature value or not needs to be judged, if the lowest air temperature and the ground temperature are lower than the preset temperature value, the snowfall is stable snowfall, the snow is in the early stage of snow accumulation from the first day of the snow accumulation period to the front of the snowfall, and if the lowest air temperature and the ground temperature are lower than the preset temperature value, the snowfall continues to be searched backwards until the stable snowfall meeting the requirements is found.
The preset temperature value of the lowest temperature alpha days after the snowfall day can be obtained by the average value of the lowest temperatures in the snow accumulation stabilization period in the historical data of many years. The preset temperature value of the average ground temperature can be obtained by the average value of the ground temperature of 0cm in the snow accumulation stabilization period in the historical data of many years. For the number of days α, twice the average number of days in the historical data that the reflectivity of the ground is higher than the preset reflectivity value after snow falls over from the previous snow accumulation period.
In this embodiment, the training samples of the data processing model include ground reflectivity data samples, and the reflectivity determination method can be used to determine the early stage of snow accumulation.
If the data missing period in this embodiment is aimed at, since there is no ground reflectivity data, it can be determined whether it is in the early stage of snow accumulation by using the lowest air temperature and the ground temperature of 0 cm.
Referring to FIG. 3, FIG. 3 includes data for the reflectance of the floor in Haerbin Shuangcheng 201911-202002. As can be seen from fig. 3, if the predetermined reflectance value is 0.6, the reflectance of the snowed ground of 11.12 and 11.17 cannot satisfy the condition that the reflectance is greater than the predetermined reflectance value for a plurality of consecutive days, and the snowing for 12.13 days satisfies the condition, so that 12.13 days is the first day of the stable snowing time, and the first day of the snowing period to 12 months and 13 days are the initial stage of snowing.
1.2, in the late stage of accumulated snow.
Searching forwards from the end of the snow accumulation period for a plurality of months (generally 1-2 months), if snowfall weather occurs and the ground reflectivity after snowfall is continuously larger than the preset reflectivity value, the snowfall is stable snow accumulation, and if the ground reflectivity after snowfall can not meet the requirement, searching forwards until the stable snow accumulation meeting the requirement is found. And defining the late stage of accumulated snow from the last snowing day to the end of the accumulated snow period of the stable snowfall.
If the data of the surface reflectivity of the beta days after the snowfall day are continuously lost for a plurality of days, judging whether at least one of the lowest air temperature and the average ground temperature of the beta days after the snowfall day is lower than a preset temperature value, if so, judging that the snowfall is stable snowfall, if so, judging that the snowfall is in the later stage of the snowfall from the next snowfall day to the last day of the snowfall period, and if so, continuously searching forwards until the stable snowfall meeting the conditions is found.
If there is no snowfall after the stable snowfall, the start of the late stage of snowfall is determined from the gamma days when the ground reflectivity is continuously lower than the preset reflectivity value (or at least one of the air temperature and the ground surface temperature is higher than the preset temperature value).
The preset temperature value of the lowest temperature beta days after the snowfall day can be obtained by the average value of the lowest temperatures in the snow accumulation stabilization period in the historical data of many years. The preset temperature value of the average ground temperature can be obtained by the average value of the ground temperature of 0cm in the snow accumulation stabilization period in the historical data of many years. For the number of days β, twice or more the average number of days in the historical data that the reflectivity of the ground is higher than the preset reflectivity value after the snow falls for the later period of the accumulated snow. And for gamma, an average day value or higher may be taken.
It should be noted that the preset temperature value and the preset reflectance value at the early stage of snow accumulation and the late stage of snow accumulation may be the same or different, and this embodiment is not limited.
Referring to fig. 4, fig. 4 includes geilin qian 201912-202003 ground reflectivity, and it can be seen from fig. 4 that if the predetermined reflectivity value is 0.6, the search proceeds from month 4 until the continuous multi-day ground reflectivity is greater than 0.6 after snowfall of day 1 and 6, so that day 1 and 6 is a stable snowfall day, and then the next snowfall is carried out for day 2 and 14 and the snow fall is carried out for day 2 and 14 to 4, respectively, for the snow accumulation period.
In this embodiment, the training samples of the data processing model include ground reflectivity data samples, and the reflectivity determination method can be used to determine the late stage of snow accumulation.
If the data missing time period in the embodiment is aimed at, since the data of the ground reflectivity does not exist, the mode of the lowest air temperature and the ground temperature of 0cm can be used for determining whether the time period belongs to the late stage of snow accumulation.
1.3, a snow accumulation stabilization period.
In this embodiment, the accumulated snow stabilization period is set after the early stage of accumulated snow is finished and before the late stage of accumulated snow is started.
1.4, non-snow period.
In addition to the above-mentioned pre-snow accumulation period, the snow stabilization period, and the post-snow accumulation period, other periods are called non-snow accumulation periods.
2) And according to the seasonal information of the historical year, dividing the non-snowy period into an initial non-snowy early period, an initial non-snowy middle period and an initial non-snowy later period.
Specifically, the non-snow accumulation period is generally three seasons of spring, summer and autumn, the time span is large, and the temperature, precipitation and the underlying surface are greatly changed, so that a model can be established according to seasons, and referring to fig. 5, for example, 1 segment (the beginning of the non-snow accumulation period (corresponding to the first day of the non-snow accumulation period in fig. 5) -6 months (specifically, 6.30 days) is called as an initial non-snow accumulation early period), 2 segments (7 months (7.1 days) -8 months (8.30 days) is called as an initial non-snow accumulation middle period), and 3 segments (9 months (9.1 days) -the end of the non-snow accumulation period (corresponding to the last day of the non-snow accumulation period in fig. 5) is called as an initial non-snow accumulation late period. The upper four points in fig. 5 correspond to the first, 6.30, 8.30 and last non-snowy date, respectively.
3) Correcting a first demarcation time point of the initial early stage of non-snow and the initial middle stage of non-snow, and a second demarcation time point of the initial middle stage of non-snow and the initial late stage of non-snow.
The first time point of demarcation is the above-mentioned 6.30 days, and the second time point of demarcation is the above-mentioned 8.30 days.
For the seasonal division, there may be a practical situation that the divided time period is not suitable for the year, so that the above-mentioned several division time points also need to be corrected by using the ground reflectivity turning points of the years of historical data.
In this embodiment, the turning point is found for correction. The measurement method of the turning point is to find the local lowest point of the ground reflectivity in three segments (the above-mentioned segments 1,2 and 3) in the non-snow accumulation period, and take the local lowest point as the turning point. The first lowest point ranges from the midpoint of the first day of the non-snowy period to the midpoint of the 2 segments, and the second lowest point ranges from the midpoint of the 2 segments to the last day of the non-snowy period.
The elliptic circles are respectively a turning point of 1-2 sections and a turning point of 2-3 sections, which are respectively called as a first ground reflectivity lowest point and a second ground reflectivity lowest point. It can be seen that there is some deviation between the turning point and the seasonal division described above. If the two lowest points are located in the 2 sections, the positions of the lowest points cannot be obtained in the 1 and 3 sections by finding the minimum value, so that the separation points of each section in the non-snow accumulation period need to be corrected by using the multi-year historical data, and the two lowest points are respectively located in the 1 and 3 sections as much as possible.
Assuming that the turn point time of the 1 st and 2 nd sections of the ground reflectivity in the nth year is T1 n, and the turn point is taken as the time Ta, wherein Ta is required to be later than A% in the nth year, and A is 0-100, for example 90%. The turning point time of the 2 nd and 3 rd sections of the ground reflectivity is T2n, and n years, the turning point time Tb is taken as the turning point, wherein Tb is required to be later than B% in the n years, and B is 0-100, such as 90%.
Ta is the 1 st, 2 nd seasonal division time point, referred to as the modified first division time point, and Tb is the 2 nd, 3 rd seasonal division time point, referred to as the modified second division time point.
4) And splitting the non-snow accumulation period by using the corrected first boundary time point and the second boundary time point to obtain a non-snow accumulation early stage, a non-snow accumulation middle stage and a non-snow accumulation later stage.
The non-snow accumulation period can be divided into three time periods by the Ta and the Tb, and the time periods are the non-snow accumulation early period, the non-snow accumulation middle period or the non-snow accumulation late period in sequence.
And S22, judging the weather data corresponding to the data missing time period according to the determination rule of the weather state time period so as to determine the weather state time period corresponding to the data missing time period.
After determining each weather state time slot and the corresponding determination rule, determining the weather data corresponding to the data missing time slot, specifically, when determining, because the weather data carries a date, preliminarily determining whether the date belongs to an accumulated snow period or a non-accumulated snow period according to a time difference between the date and a first day and a last day of the accumulated snow period, then determining whether the date accords with the determination rule of each sub-period in the period, and if so, determining that the date belongs to the sub-period. If not, continuously judging whether the current sub-period belongs to the next sub-period.
In this embodiment, a judgment basis of each weather state time period is provided, and then the weather state time period corresponding to the data missing time period can be determined according to the judgment basis of each weather state time period, and a data processing model suitable for the data missing time period can be selected for missing value prediction.
In another implementation of the present invention, a "generation process of a data processing model" is provided, and with reference to fig. 6, the generation process may include:
and S31, obtaining a training sample.
The training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
The weather data sample in the present embodiment is weather data in recent years. For example, data of a year in which the data missing ratio does not exceed the preset ratio in the last 10 years is selected.
In practical applications, referring to fig. 7, step S31 may include:
and S41, acquiring an initial weather data sample corresponding to the weather state time period.
In this embodiment, the initial weather data sample of the year in which the data missing proportion does not exceed the preset proportion in the last 10 years may be screened, and the initial weather data sample includes weather data of a plurality of indexes in different time periods. Such as weather data for each day including the year of the screening. The weather data may be data corresponding to the maximum daily temperature, the minimum daily temperature, the ground temperature of 0cm, the amount of snow fall (the judgment criterion is that the rainfall occurs, and the amount of snow fall is the amount of snow fall when the weather is snow instead of rain), the precipitation data, the humidity, and the like.
The maximum daily temperature, the minimum daily temperature, the ground temperature of 0cm, the amount of snow (the judgment standard is that precipitation occurs, and the amount of snow is snow instead of rain in the day), precipitation data, and humidity are the indexes provided in the embodiment.
On the basis of this embodiment, in another implementation manner of the present invention, a specific implementation process of step S41 is given, and with reference to fig. 8, the implementation process may include:
s51, based on the preset weather state periods and the determination rules of the weather state periods, the historical years are divided into a non-snow early stage, a non-snow middle stage, a non-snow later stage, a snow early stage, a snow stabilization stage and a snow later stage.
In practical application, the specific implementation process is as follows:
1) dividing the historical years into a non-snow period, a snow accumulation early period, a snow accumulation stabilizing period and a snow accumulation later period based on the preset weather state periods and the determination rule of the weather state periods;
2) according to the seasonal information of the historical year, dividing the non-snowy period into an initial non-snowy early period, an initial non-snowy middle period and an initial non-snowy later period;
3) correcting a first demarcation time point of the initial early stage of non-snow and the initial middle stage of non-snow, and a second demarcation time point of the initial middle stage of non-snow and the initial late stage of non-snow;
4) and splitting the non-snow accumulation period by using the corrected first boundary time point and the second boundary time point to obtain a non-snow accumulation early stage, a non-snow accumulation middle stage and a non-snow accumulation later stage.
It should be noted that, the specific implementation process of these several steps refers to the corresponding description in the above embodiments.
S52, acquiring initial weather data samples corresponding to the early stage of non-snow, the middle stage of non-snow, the late stage of non-snow, the early stage of snow, the stable stage of snow and the late stage of snow in the historical year.
Specifically, after the year is divided into the time periods, the weather data is also divided according to the time periods, so as to obtain an initial weather data sample of each time period.
And S53, screening out the initial weather data samples corresponding to the weather state time period from the initial weather data samples.
In this embodiment, the weather state time period is one of the time periods, so that the time period to which the weather state time period belongs can be determined, and the initial weather data sample corresponding to the time period can be obtained.
S42, based on the weather data of the multiple indexes in different time periods, screening out key indexes corresponding to the weather state time periods from the multiple indexes.
Specifically, not all of the above-mentioned multiple indexes are highly correlated with the weather state time period, so for each of the above-mentioned weather state time periods, it is necessary to select a key index highly correlated with the weather state time period from the above-mentioned multiple indexes.
Aiming at the early stage of accumulated snow, the stable stage of accumulated snow and the later stage of accumulated snow, as no precipitation data exists in the snow stage, key indexes are screened out from the highest daily temperature, the lowest daily temperature, the ground temperature of 0cm, the snow precipitation amount (the judgment standard is that precipitation occurs, and the weather is snow instead of rain, and the precipitation amount is the snow precipitation amount) and the humidity.
For the non-snow period, including the non-snow early period, the non-snow middle period or the non-snow later period, precipitation data exist, but the precipitation amount does not exist, so that key indexes can be screened from the highest daily temperature, the lowest daily temperature, humidity, the ground temperature of 0cm and precipitation data.
When the key indexes are screened out from the multiple indexes, the specific implementation process can be as follows:
and calculating the correlation of the weather data of the multiple indexes at different time periods to obtain the correlation among the multiple indexes, screening out the indexes meeting a preset correlation rule from the multiple indexes based on the correlation among the multiple indexes, and using the indexes as key indexes corresponding to the weather state time periods.
Specifically, the correlation calculation may use a corel function in EXCEL, or calculate according to a pearson correlation coefficient method, calculate the correlation between multiple indexes, rank the correlation to avoid overfitting, and select a plurality of indexes with high correlation, for example, three indexes, as key indexes (the number of indexes does not exceed half of the total number to avoid overfitting).
And S43, taking the weather data of the key indexes in different time periods as weather data samples corresponding to the weather state time periods.
Specifically, the weather data of the key indexes in different time periods are screened out from the weather data of the indexes in different time periods, and then the weather data are used as weather data samples corresponding to the weather state time periods.
And S44, acquiring the ground reflectivity data sample corresponding to each time period in the weather data samples.
In particular, the surface reflectance data may be acquired each day of the year and sampled as surface reflectance data.
And S32, training the data processing model by using the training samples until a preset training stopping condition is reached.
In this embodiment, the data processing model may be a neural network model, a machine learning model, or the like, and the preset training stop condition in this embodiment is that the loss function value is smaller than the preset loss value.
It should be noted that, for the early stage of snow accumulation, the stable stage of snow accumulation and the late stage of snow accumulation, a data processing model is respectively created.
Aiming at the non-snow period, if the resources are saved, only one data processing model is created in the whole non-snow period. If the accuracy is improved, different data processing models can be created for three time periods, namely the early stage of non-snow accumulation, the middle stage of non-snow accumulation or the late stage of non-snow accumulation.
In the embodiment, the ground reflectivity is modeled by using the temperature and precipitation data, the influence of the accumulated snow on the ground reflectivity is considered, and the change of the accumulated snow reflectivity along with environmental factors such as temperature and the like is also considered, so that the repaired data missing value is more in line with the actual requirement than the data missing value by using an interpolation method.
In addition, segmented learning modeling is carried out on the data of the snow accumulation period and the data of the non-snow accumulation period, so that a ground reflectivity model can be better provided. Missing data for longer periods of time, including the case where the ground reflectivity was not updated in time for the last months. Relevant data (temperature, humidity, precipitation, etc.) may be brought into the established models of ground reflectivity for snow and non-snow periods, giving longer periods of predicted ground reflectivity.
On the basis of the embodiment of the method for determining reflectivity data, another embodiment of the present invention provides a method for determining an electric quantity, and with reference to fig. 9, the method may include:
s61, acquiring the ground reflectivity data of the data missing time period; the ground reflectivity data is determined by the method for determining the reflectivity data;
and S62, determining the power generation amount of the double-sided photovoltaic module by using the ground reflectivity data.
In practical application, the power generation amount determination mode can be set by a technician according to an actual scene.
In this embodiment, the accuracy of the ground reflectivity data determined by the method for determining reflectivity data is high, and the accuracy of the generated energy of the double-sided photovoltaic module obtained by using the data with high accuracy is also high.
Alternatively, on the basis of the embodiment of the method for determining reflectivity data, another embodiment of the present invention provides a device for determining reflectivity data, and referring to fig. 10, the device may include:
the weather data acquisition module 11 is configured to acquire a data missing time period and acquire weather data corresponding to the data missing time period;
a time period determining module 12, configured to determine, based on the weather data, a weather state time period corresponding to the data missing time period;
the data determining module 13 is configured to obtain a data processing model corresponding to the weather state time period, and call the data processing model to process the weather data to obtain ground reflectivity data of the data missing time period;
the data processing model is obtained based on training of a training sample; the training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
Further, the period determination module 12 includes:
the data acquisition submodule is used for acquiring preset weather state time periods and a determination rule of the weather state time periods; each weather state time interval comprises a non-snow accumulation period, a snow accumulation early period, a snow accumulation stabilization period and a snow accumulation later period; the non-snow period comprises at least one non-snow time period;
and the state determining submodule is used for judging the weather data corresponding to the data missing time period according to the determining rule of the weather state time period so as to determine the weather state time period corresponding to the data missing time period.
Further, in a case where the non-snow period includes a plurality of non-snow periods, the non-snow periods include a pre-non-snow period, a mid-non-snow period, or a post-non-snow period.
Furthermore, the data processing models corresponding to different weather state time periods are different, and the reflectivity data determining device further comprises a model generating module;
the model generation module includes:
the sample generation submodule is used for acquiring a training sample; the training samples comprise weather data samples corresponding to the weather state period and ground reflectivity data samples;
and the training submodule is used for training the data processing model by using the training sample until a preset training stopping condition is reached.
The sample generation submodule comprises:
the first sample acquisition unit is used for acquiring an initial weather data sample corresponding to the weather state time period; the initial weather data sample comprises weather data of a plurality of indexes at different time periods;
the index screening module is used for screening out key indexes corresponding to the weather state time periods from the multiple indexes on the basis of the weather data of the multiple indexes at different time periods;
the sample determining unit is used for taking the weather data of the key indexes in different time periods as weather data samples corresponding to the weather state time periods;
and the second sample acquisition unit is used for acquiring the ground reflectivity data sample corresponding to each time period in the weather data samples.
Further, the first sample acquiring unit includes:
the splitting subunit is used for splitting the historical year into a non-snow accumulation early stage, a non-snow accumulation middle stage, a non-snow accumulation later stage, a snow accumulation early stage, a snow accumulation stabilizing stage and a snow accumulation later stage on the basis of the preset weather state periods and the determination rules of the weather state periods;
the sample acquiring subunit is used for acquiring initial weather data samples respectively corresponding to the early stage of non-snow, the middle stage of non-snow, the late stage of non-snow, the early stage of snow, the stable stage of snow and the late stage of snow in the historical year;
and the screening subunit is used for screening out the initial weather data samples corresponding to the weather state time period from the initial weather data samples.
Further, the splitting subunit is specifically configured to:
dividing the historical years into a non-snow period, a snow accumulation early period, a snow accumulation stabilizing period and a snow accumulation later period based on the preset weather state periods and the determination rule of the weather state periods;
according to the seasonal information of the historical year, dividing the non-snowy period into an initial non-snowy early period, an initial non-snowy middle period and an initial non-snowy later period;
correcting a first demarcation time point of the initial early stage of non-snow and the initial middle stage of non-snow, and a second demarcation time point of the initial middle stage of non-snow and the initial late stage of non-snow;
and splitting the non-snow accumulation period by using the corrected first boundary time point and the second boundary time point to obtain a non-snow accumulation early stage, a non-snow accumulation middle stage and a non-snow accumulation later stage.
Further, the index screening module includes:
the correlation degree operator module is used for calculating the correlation degree of the weather data of the multiple indexes at different time periods to obtain the correlation degree among the multiple indexes;
and the index screening submodule is used for screening out indexes meeting a preset correlation rule from the multiple indexes based on the correlation among the multiple indexes and taking the indexes as key indexes corresponding to the weather state time period.
In this embodiment, when the ground reflectivity data of a certain time period is missing, the data processing model can be used to predict the ground reflectivity data of the data missing time period, and thus the ground reflectivity data can be used to determine the power generation amount of the double-sided photovoltaic module. Further, in the method and the device, before the ground reflectivity data is predicted, the weather state time period corresponding to the data missing time period is determined based on the weather data corresponding to the data missing time period, and then the data processing model matched with the weather state time period is selected, so that the called data processing model considers the weather state of the data missing time period, and the accuracy of the data processing model is improved.
It should be noted that, for the working processes of each module, sub-module, unit, and sub-unit in this embodiment, please refer to the corresponding description in the above embodiments, which is not repeated herein.
Optionally, on the basis of the embodiment of the power determining method, another embodiment of the present invention provides a power determining apparatus, with reference to fig. 11, including:
a reflectivity data obtaining module 21, configured to obtain ground reflectivity data of the data missing time period; the ground reflectivity data is determined by the method for determining the reflectivity data;
and the power generation capacity determining module 22 is used for determining the power generation capacity of the double-sided photovoltaic module by using the ground reflectivity data.
In this embodiment, the accuracy of the ground reflectivity data determined by the method for determining reflectivity data is high, and the accuracy of the generated energy of the double-sided photovoltaic module obtained by using the data with high accuracy is also high.
It should be noted that, for the working process of each module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Alternatively, on the basis of the embodiments of the reflectivity data determining method and the power amount determining method, another embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, and when the program runs, a device in which the storage medium is located is controlled to execute the reflectivity data determining method or the power amount determining method.
Alternatively, on the basis of the above embodiments of the method for determining reflectance data and the method for determining an amount of electricity, another embodiment of the present invention provides an electronic device, including: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used for executing the determination method of the reflectivity data or executing the electric quantity determination method.
In this embodiment, when the ground reflectivity data of a certain time period is missing, the data processing model can be used to predict the ground reflectivity data of the data missing time period, and thus the ground reflectivity data can be used to determine the power generation amount of the double-sided photovoltaic module. Further, in the method and the device, before the ground reflectivity data is predicted, the weather state time period corresponding to the data missing time period is determined based on the weather data corresponding to the data missing time period, and then the data processing model matched with the weather state time period is selected, so that the called data processing model considers the weather state of the data missing time period, and the accuracy of the data processing model is improved.
In addition, in this embodiment, the accuracy of the ground reflectivity data determined by the method for determining reflectivity data is higher, and the accuracy of the generated energy of the double-sided photovoltaic module obtained by using the data with higher accuracy is also higher.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (13)
1. A method for determining reflectivity data, comprising:
acquiring a data missing time period and acquiring weather data corresponding to the data missing time period;
determining a weather state period corresponding to the data missing time period based on the weather data;
acquiring a data processing model corresponding to the weather state time period, and calling the data processing model to process the weather data to obtain the ground reflectivity data of the data missing time period;
the data processing model is obtained based on training of a training sample; the training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
2. The determination method according to claim 1, wherein determining the weather state period corresponding to the data missing time period based on the weather data comprises:
acquiring preset weather state time periods and a determination rule of the weather state time periods; each weather state time interval comprises a non-snow accumulation period, a snow accumulation early period, a snow accumulation stabilization period and a snow accumulation later period; the non-snow period comprises at least one non-snow time period;
and judging the weather data corresponding to the data missing time period according to the determination rule of the weather state time period so as to determine the weather state time period corresponding to the data missing time period.
3. The determination method according to claim 2, wherein in the case where the period of non-snow cover includes a plurality of periods of non-snow cover, the period of non-snow cover includes a pre-period of non-snow cover, a mid-period of non-snow cover, or a post-period of non-snow cover.
4. The determination method according to claim 3, wherein the data processing models corresponding to different weather condition periods are different, and the generation process of the data processing models comprises:
obtaining a training sample; the training samples comprise weather data samples corresponding to the weather state period and ground reflectivity data samples;
and training a data processing model by using the training samples until a preset training stopping condition is reached.
5. The method of claim 4, wherein obtaining training samples comprises:
acquiring an initial weather data sample corresponding to the weather state time period; the initial weather data sample comprises weather data of a plurality of indexes at different time periods;
screening out key indexes corresponding to the weather state time periods from the multiple indexes on the basis of the weather data of the multiple indexes at different time periods;
taking the weather data of the key indexes at different time periods as weather data samples corresponding to the weather state time periods;
and acquiring a ground reflectivity data sample corresponding to each time period in the weather data samples.
6. The method of claim 5, wherein obtaining the initial weather data sample corresponding to the weather condition period comprises:
dividing the historical year into a non-snow accumulation early stage, a non-snow accumulation middle stage, a non-snow accumulation later stage, a snow accumulation early stage, a snow accumulation stabilization stage and a snow accumulation later stage based on the preset weather state periods and the determination rule of the weather state periods;
acquiring initial weather data samples respectively corresponding to the early stage of non-accumulated snow, the middle stage of non-accumulated snow, the late stage of non-accumulated snow, the early stage of accumulated snow, the stable stage of accumulated snow and the late stage of accumulated snow in the historical year;
and screening out the initial weather data samples corresponding to the weather state time period from the initial weather data samples.
7. The determination method according to claim 6, wherein the dividing of the historical year into the non-pre-snow period, the non-mid-snow period, the non-post-snow period, the pre-snow period, the snow stationary period, and the post-snow period based on the preset weather condition periods and the determination rule of the weather condition periods comprises:
dividing the historical years into a non-snow period, a snow accumulation early period, a snow accumulation stabilizing period and a snow accumulation later period based on the preset weather state periods and the determination rule of the weather state periods;
according to the seasonal information of the historical year, dividing the non-snowy period into an initial non-snowy early period, an initial non-snowy middle period and an initial non-snowy later period;
correcting a first demarcation time point of the initial early stage of non-snow and the initial middle stage of non-snow, and a second demarcation time point of the initial middle stage of non-snow and the initial late stage of non-snow;
and splitting the non-snow accumulation period by using the corrected first boundary time point and the second boundary time point to obtain a non-snow accumulation early stage, a non-snow accumulation middle stage and a non-snow accumulation later stage.
8. The determination method according to claim 5, wherein screening out a key index corresponding to the weather condition period from the plurality of indexes based on the weather data of the plurality of indexes at different time periods comprises:
performing correlation calculation on the weather data of the multiple indexes at different time periods to obtain correlation among the multiple indexes;
and screening out indexes meeting preset correlation rule from the indexes based on the correlation among the indexes, and using the indexes as key indexes corresponding to the weather state time period.
9. A method for determining an amount of power, comprising:
acquiring the ground reflectivity data of the data missing time period; the ground reflectivity data is determined by the method of determining reflectivity data of any one of claims 1-8;
and determining the power generation capacity of the double-sided photovoltaic module by using the ground reflectivity data.
10. An apparatus for determining reflectivity data, comprising:
the weather data acquisition module is used for acquiring a data missing time period and acquiring weather data corresponding to the data missing time period;
the time interval determining module is used for determining a weather state time interval corresponding to the data missing time interval based on the weather data;
the data determining module is used for acquiring a data processing model corresponding to the weather state time period and calling the data processing model to process the weather data to obtain the ground reflectivity data of the data missing time period;
the data processing model is obtained based on training of a training sample; the training samples include weather data samples corresponding to the weather condition periods and ground reflectivity data samples.
11. An electrical quantity determination device, comprising:
the reflectivity data acquisition module is used for acquiring the ground reflectivity data of the data missing time period; the ground reflectivity data is determined by the method of determining reflectivity data of any one of claims 1-8;
and the power generation capacity determining module is used for determining the power generation capacity of the double-sided photovoltaic module by using the ground reflectivity data.
12. A storage medium characterized by comprising a stored program, wherein a device on which the storage medium is located is controlled to execute the determination method of the reflectivity data according to any one of claims 1 to 8 or the determination method of the amount of electricity according to claim 9 when the program is run.
13. An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to perform the method of determining reflectance data according to any one of claims 1 to 8 or to perform the method of determining an amount of electricity according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938005.9A CN113627546A (en) | 2021-08-16 | 2021-08-16 | Method for determining reflectivity data, method for determining electric quantity and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938005.9A CN113627546A (en) | 2021-08-16 | 2021-08-16 | Method for determining reflectivity data, method for determining electric quantity and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627546A true CN113627546A (en) | 2021-11-09 |
Family
ID=78385706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110938005.9A Pending CN113627546A (en) | 2021-08-16 | 2021-08-16 | Method for determining reflectivity data, method for determining electric quantity and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627546A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005825A (en) * | 2015-07-03 | 2015-10-28 | 深圳供电局有限公司 | Method and system for predicting photovoltaic power based on dynamic neural network |
| US20160307138A1 (en) * | 2015-04-14 | 2016-10-20 | International Business Machines Corporation | Weather-driven multi-category infrastructure impact forecasting |
| CN106447131A (en) * | 2016-10-24 | 2017-02-22 | 易事特集团股份有限公司 | Independent microgrid photovoltaic output power prediction method and energy regulation method |
| CN106779223A (en) * | 2016-12-21 | 2017-05-31 | 创维互联（北京）新能源科技有限公司 | A kind of photovoltaic system electricity generation power real-time predicting method and device |
| CN107220723A (en) * | 2017-04-20 | 2017-09-29 | 华北电力大学 | A kind of predicting power of photovoltaic plant method |
| CN109858665A (en) * | 2018-12-06 | 2019-06-07 | 国网河北省电力有限公司 | Photovoltaic short term power prediction technique based on Feature Selection and ANFIS-PSO |
| US20200057175A1 (en) * | 2018-08-17 | 2020-02-20 | Nec Laboratories America, Inc. | Weather dependent energy output forecasting |
| CN111507495A (en) * | 2019-01-30 | 2020-08-07 | 北京金风科创风电设备有限公司 | Method and device for predicting missing wind measurement data |
| CN113239722A (en) * | 2021-03-31 | 2021-08-10 | 成都信息工程大学 | Deep learning based strong convection extrapolation method and system under multi-scale |
-
2021
- 2021-08-16 CN CN202110938005.9A patent/CN113627546A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160307138A1 (en) * | 2015-04-14 | 2016-10-20 | International Business Machines Corporation | Weather-driven multi-category infrastructure impact forecasting |
| CN105005825A (en) * | 2015-07-03 | 2015-10-28 | 深圳供电局有限公司 | Method and system for predicting photovoltaic power based on dynamic neural network |
| CN106447131A (en) * | 2016-10-24 | 2017-02-22 | 易事特集团股份有限公司 | Independent microgrid photovoltaic output power prediction method and energy regulation method |
| CN106779223A (en) * | 2016-12-21 | 2017-05-31 | 创维互联（北京）新能源科技有限公司 | A kind of photovoltaic system electricity generation power real-time predicting method and device |
| CN107220723A (en) * | 2017-04-20 | 2017-09-29 | 华北电力大学 | A kind of predicting power of photovoltaic plant method |
| US20200057175A1 (en) * | 2018-08-17 | 2020-02-20 | Nec Laboratories America, Inc. | Weather dependent energy output forecasting |
| CN109858665A (en) * | 2018-12-06 | 2019-06-07 | 国网河北省电力有限公司 | Photovoltaic short term power prediction technique based on Feature Selection and ANFIS-PSO |
| CN111507495A (en) * | 2019-01-30 | 2020-08-07 | 北京金风科创风电设备有限公司 | Method and device for predicting missing wind measurement data |
| CN113239722A (en) * | 2021-03-31 | 2021-08-10 | 成都信息工程大学 | Deep learning based strong convection extrapolation method and system under multi-scale |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108091166B (en) | Method, device, equipment and storage medium for predicting number change of available parking spaces | |
| CN113592165B (en) | Sub-season climate prediction method and system based on ten-day trend and physical mode modeling | |
| JP2006033908A (en) | Method, device and program for estimating amount of power generation of solar light generating system | |
| CN113505927B (en) | Method, device, equipment and medium for selecting battery capacity of solar bird repelling equipment | |
| CN116070728B (en) | Photovoltaic power generation system power generation amount prediction method, device, system and medium | |
| CN106291764A (en) | Based on big data and the method for meteorological forecast of meteorologic analysis field and system | |
| KR20200052432A (en) | Electronic device for predicting long-term photovoltaic power generation using meteorological and seasonal information based on deep learning and operating method thereof | |
| CN115936177A (en) | Photovoltaic output power prediction method and system based on neural network | |
| CN107145714B (en) | Multi-factor-based public bicycle usage amount prediction method | |
| CN115271253A (en) | Water-wind power generation power prediction model construction method and device and storage medium | |
| CN113627546A (en) | Method for determining reflectivity data, method for determining electric quantity and related device | |
| CN116739172B (en) | Method and device for ultra-short-term prediction of offshore wind power based on climbing identification | |
| CN103578274B (en) | A kind of traffic flow forecasting method and device | |
| CN110969296B (en) | Electric heating load prediction method and device and terminal equipment | |
| CN113435661B (en) | Method, device, medium, and apparatus for estimating rainstorm peak position | |
| CN116247644A (en) | Charging and discharging method and device based on energy storage system, storage medium and terminal | |
| CN114911301A (en) | Maximum power tracking control method, photovoltaic system and energy storage equipment | |
| CN110928634B (en) | Data processing method, device and equipment | |
| CN112163695A (en) | Copula function-based wind power photovoltaic power generation prediction method, system and medium | |
| CN104952131A (en) | Method and device for visitor's visit time register of building intercom system | |
| CN104794547A (en) | Temperature based power load data long-term prediction method | |
| CN114818317A (en) | Precipitation intensity-duration-frequency curve generation method and system | |
| CN117217822B (en) | Method, device, terminal equipment and storage medium for predicting power transaction index | |
| CN117650525A (en) | Power grid load prediction method and device, medium and electronic equipment | |
| CN114048905A (en) | Price prediction method, device, equipment and storage medium of power resource |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: High tech Zone of Hefei city of Anhui Province in 230088 Lake Road No. 2 Applicant after: Sunshine New Energy Development Co.,Ltd. Address before: High tech Zone of Hefei city of Anhui Province in 230088 Lake Road No. 2 Applicant before: Sunshine New Energy Development Co.,Ltd. |
|
| CB02 | Change of applicant information |